five

open-llm-leaderboard-old/details_xxyyy123__test_qkvo_adptor

收藏
Hugging Face2023-09-03 更新2024-06-22 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_xxyyy123__test_qkvo_adptor
下载链接
链接失效反馈
官方服务:
资源简介:
该数据集是在模型xxyyy123/test_qkvo_adptor的评估运行期间自动创建的,用于在Open LLM Leaderboard上进行评估。数据集由61个配置组成,每个配置对应一个评估任务。数据集是从1次运行中创建的,每次运行都可以在特定配置中找到,分割名称使用运行的时间戳。train分割始终指向最新结果。此外,results配置存储了所有运行的聚合结果,并用于计算和显示Open LLM Leaderboard上的聚合指标。

该数据集是在模型xxyyy123/test_qkvo_adptor的评估运行期间自动创建的,用于在Open LLM Leaderboard上进行评估。数据集由61个配置组成,每个配置对应一个评估任务。数据集是从1次运行中创建的,每次运行都可以在特定配置中找到,分割名称使用运行的时间戳。train分割始终指向最新结果。此外,results配置存储了所有运行的聚合结果,并用于计算和显示Open LLM Leaderboard上的聚合指标。
提供机构:
open-llm-leaderboard-old
原始信息汇总

数据集概述

数据集组成

  • 数据集包含61个配置,每个配置对应一个评估任务。
  • 数据集由1次运行生成,每个运行可以在每个配置中找到特定的分割,分割名称使用运行的时间戳。
  • "train"分割始终指向最新结果。
  • 额外的"results"配置存储所有运行的聚合结果,用于计算和显示在Open LLM Leaderboard上的聚合指标。

最新结果

  • 最新结果来自2023-09-03T04:28:57.572800的运行,包含多个任务的评估结果。

配置详情

  • harness_arc_challenge_25

    • 分割:2023_09_03T04_28_57.572800
    • 路径:**/details_harness|arc:challenge|25_2023-09-03T04:28:57.572800.parquet
    • 分割:latest
    • 路径:**/details_harness|arc:challenge|25_2023-09-03T04:28:57.572800.parquet
  • harness_hellaswag_10

    • 分割:2023_09_03T04_28_57.572800
    • 路径:**/details_harness|hellaswag|10_2023-09-03T04:28:57.572800.parquet
    • 分割:latest
    • 路径:**/details_harness|hellaswag|10_2023-09-03T04:28:57.572800.parquet
  • harness_hendrycksTest_5

    • 分割:2023_09_03T04_28_57.572800
    • 路径:
      • **/details_harness|hendrycksTest-abstract_algebra|5_2023-09-03T04:28:57.572800.parquet
      • **/details_harness|hendrycksTest-anatomy|5_2023-09-03T04:28:57.572800.parquet
      • **/details_harness|hendrycksTest-astronomy|5_2023-09-03T04:28:57.572800.parquet
      • **/details_harness|hendrycksTest-business_ethics|5_2023-09-03T04:28:57.572800.parquet
      • **/details_harness|hendrycksTest-clinical_knowledge|5_2023-09-03T04:28:57.572800.parquet
      • **/details_harness|hendrycksTest-college_biology|5_2023-09-03T04:28:57.572800.parquet
      • **/details_harness|hendrycksTest-college_chemistry|5_2023-09-03T04:28:57.572800.parquet
      • **/details_harness|hendrycksTest-college_computer_science|5_2023-09-03T04:28:57.572800.parquet
      • **/details_harness|hendrycksTest-college_mathematics|5_2023-09-03T04:28:57.572800.parquet
      • **/details_harness|hendrycksTest-college_medicine|5_2023-09-03T04:28:57.572800.parquet
      • **/details_harness|hendrycksTest-college_physics|5_2023-09-03T04:28:57.572800.parquet
      • **/details_harness|hendrycksTest-computer_security|5_2023-09-03T04:28:57.572800.parquet
      • **/details_harness|hendrycksTest-conceptual_physics|5_2023-09-03T04:28:57.572800.parquet
      • **/details_harness|hendrycksTest-econometrics|5_2023-09-03T04:28:57.572800.parquet
      • **/details_harness|hendrycksTest-electrical_engineering|5_2023-09-03T04:28:57.572800.parquet
      • **/details_harness|hendrycksTest-elementary_mathematics|5_2023-09-03T04:28:57.572800.parquet
      • **/details_harness|hendrycksTest-formal_logic|5_2023-09-03T04:28:57.572800.parquet
      • **/details_harness|hendrycksTest-global_facts|5_2023-09-03T04:28:57.572800.parquet
      • **/details_harness|hendrycksTest-high_school_biology|5_2023-09-03T04:28:57.572800.parquet
      • **/details_harness|hendrycksTest-high_school_chemistry|5_2023-09-03T04:28:57.572800.parquet
      • **/details_harness|hendrycksTest-high_school_computer_science|5_2023-09-03T04:28:57.572800.parquet
      • **/details_harness|hendrycksTest-high_school_european_history|5_2023-09-03T04:28:57.572800.parquet
      • **/details_harness|hendrycksTest-high_school_geography|5_2023-09-03T04:28:57.572800.parquet
      • **/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-09-03T04:28:57.572800.parquet
二维码
社区交流群
二维码
科研交流群
商业服务